1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
|
#ifndef __ASM_QSPINLOCK_PARAVIRT_H
#define __ASM_QSPINLOCK_PARAVIRT_H
/*
* For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit
* registers. For i386, however, only 1 32-bit register needs to be saved
* and restored. So an optimized version of __pv_queued_spin_unlock() is
* hand-coded for 64-bit, but it isn't worthwhile to do it for 32-bit.
*/
#ifdef CONFIG_64BIT
PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath);
#define __pv_queued_spin_unlock __pv_queued_spin_unlock
#define PV_UNLOCK "__raw_callee_save___pv_queued_spin_unlock"
#define PV_UNLOCK_SLOWPATH "__raw_callee_save___pv_queued_spin_unlock_slowpath"
/*
* Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock
* which combines the registers saving trunk and the body of the following
* C code:
*
* void __pv_queued_spin_unlock(struct qspinlock *lock)
* {
* struct __qspinlock *l = (void *)lock;
* u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
*
* if (likely(lockval == _Q_LOCKED_VAL))
* return;
* pv_queued_spin_unlock_slowpath(lock, lockval);
* }
*
* For x86-64,
* rdi = lock (first argument)
* rsi = lockval (second argument)
* rdx = internal variable (set to 0)
*/
asm (".pushsection .text;"
".globl " PV_UNLOCK ";"
".align 4,0x90;"
PV_UNLOCK ": "
"push %rdx;"
"mov $0x1,%eax;"
"xor %edx,%edx;"
"lock cmpxchg %dl,(%rdi);"
"cmp $0x1,%al;"
"jne .slowpath;"
"pop %rdx;"
"ret;"
".slowpath: "
"push %rsi;"
"movzbl %al,%esi;"
"call " PV_UNLOCK_SLOWPATH ";"
"pop %rsi;"
"pop %rdx;"
"ret;"
".size " PV_UNLOCK ", .-" PV_UNLOCK ";"
".popsection");
#else /* CONFIG_64BIT */
extern void __pv_queued_spin_unlock(struct qspinlock *lock);
PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock);
#endif /* CONFIG_64BIT */
#endif
|
